Advanced Convolutional Neural Network Architecture : A Detailed Review

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2019 by IJETT Journal
Volume-67 Issue-5
Year of Publication : 2019
Authors : Suresh Arunachalam T, Shahana R, Kavitha T
  10.14445/22315381/IJETT-V67I5P231

MLA 

MLA Style: Suresh Arunachalam T, Shahana R, Kavitha T"Advanced Convolutional Neural Network Architecture : A Detailed Review" International Journal of Engineering Trends and Technology 67.5 (2019):183-187.

APA Style: Suresh Arunachalam T, Shahana R, Kavitha T (2019).Advanced Convolutional Neural Network Architecture : A Detailed Review International Journal of Engineering Trends and Technology,67(5),183-187

Abstract
Deep Learning is a part of Machine Learning algorithm. It looks and works like a brain, it is also known as Artificial Neural Networks and it is trained from a large amount of data. Now-a-days deep learning technology plays a vital role in many fields such as an object detection, classification, image segmentation and recognition. In this paper, we discussed benefits, issues and applications of advanced architecture available in deep learning networks. Generally, deep learning architecture consists of three layers namely, input layer, hidden layers (Convolutional layers, Pooling layers and activation layers), and output layer. The learning can be achieved by any of the supervised, unsupervised, reinforcement algorithms. The common issues in the architectures fall under the requirement for larger dataset to train the neural network and it consumes more time to train the network.

Reference
[1] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool. Speeded-up robust features (surf). CVIU, 110(3):346–359, 2008.
[2] C. Cortes and V. Vapnik. Support-vector networks. Machine learning, 20(3):273–297, 1995.
[3] Moving Object Detection and Locating Based on Region Shrinking Algorithm, Zhihui Li, Haibo Liu and Di Sun, IEEE 2012.
[4] R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR, 2014.
[5] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105, 2012.
[6] S. Ren, K. He, R. Girshick, and J. Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pages 91–99, 2015.
[7] K. He, X. Zhang, S. Ren, and J. Sun. (Dec. 2015). ``Deep residual learning for image recognition.'' [Online]. Available: https://arxiv.org/abs/1512.03385
[8] M. Iliadis, L. Spinoulas, and A. K. Katsaggelos, ``Deep fully-connected networks for video compressive sensing,'' Digit. Signal Process., vol. 72, pp. 9_18, Jan. 2018.
[9] J. Kim, J. Kim, H. L. T. Thu, and H. Kim, ``Long short term memory recurrent neural network classifier for intrusion detection,'' in Proc. Int. Conf. Platform Technol. Service (PlatCon), Feb. 2016, pp. 1_5.

Keywords
Deep Learning, Advanced Architecture, CNN.